Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add pnp/sharepoint-skills --skill campaign-storygit clone --depth 1 https://github.com/pnp/sharepoint-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/pnp/sharepoint-skills/campaign-story)<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/campaign-story"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/campaign-story/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/pnp/sharepoint-skills/campaign-story"><img src="https://agentmods.dev/badge/skills/pnp/sharepoint-skills/campaign-story.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00103 | $0.01015 |
| Opus 5.5 | $0.00041 | $0.00406 |
| Sonnet 5.5 | $0.00021 | $0.00203 |
| Haiku 4.5 | $0.00010 | $0.00102 |
Grade A, and why
campaign-story scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 59 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Campaign Story
When to use
Use this skill to turn a product narrative, B2B customer case, product launch, operational transformation, or campaign idea into a self-contained animated HTML story. Create HTML only unless the user explicitly requests another format.
Use a tight campaign arc rather than a slide deck. The default is a one-minute story with 5–6 scenes:
- Pain point
- Moment one — first improvement
- Moment two — second improvement
- Moment three — third improvement
- Measurable outcome
- Campaign payoff and CTA
Inputs
- A source document, user brief, or named SharePoint file.
- Optional audience, product name, customer name, CTA, length, language, and destination.
- If no source is provided, create a clearly fictional story and label every invented company, person, quote, result, and metric as fictional.
Steps
- Read the supplied source before writing. Use only source facts, figures, customer names, and quotes. If there is no source, build a fictional sample.
- Write concise scene data. Keep narration to 45 words or fewer per scene. Use clear everyday language designed to be heard.
- Use the campaign arc above unless the user gives a different structure. Make each journey beat a discrete, useful change rather than a vague benefit.
- Build a complete HTML file with no external images, fonts, libraries, network calls, CDNs, or script imports.
- Use the NexusFlow design system:
- premium, subject-led B2B application interface, not a slide deck;
- high-contrast ink, paper, operational blue, electric-blue emphasis, restrained green success state, and semantic progress rail;
- strong purposeful type scale, sentence-case labels, clear hierarchy, fine functional borders, and an uncluttered layout;
- avoid generic AI dashboard tropes such as glassmorphism, decorative gradient orbs, excessive pill UI, newspaper styling, all-caps metadata overload, and ornamental arrows;
- cards slide in for each journey beat, with one action per card — see, assign, act, or an equivalent story-specific sequence;
- animate checkmark icons when a key action completes;
- use a bold measurable result scene with a count-up metric;
- use a full confetti burst only on the final campaign-payoff scene.
- Keep interactions snappy and purposeful — slide scene transitions, card entrance motion, pulsing primary playback button, count-ups, checkmarks, word-by-word captions, scene progress, and clickable progress segments. Respect
prefers-reduced-motion. - Include playback controls — play/pause, previous, next, restart, narration on/off, voice picker, and speed picker. Do not include a full-screen control.
- Narration is ON by default. On load, attempt to speak the first scene with browser
speechSynthesis. Populate the voice picker from installed English browser/system voices plus a Default voice option. When the user changes voice, restart the current scene narration with that choice. - Browsers can block audible autoplay. If narration cannot start until a user gesture, retain the enabled state and show the in-stage message
Narration is ready — select Play to hear it.Start narration after the first click, tap, or keypress. Never claim automatic sound is guaranteed. - Synchronize caption highlighting and progress with narration. Each narrated scene must wait for speech to finish before auto-advancing.
- Save every completed HTML animation to the site’s Reports library.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 4d ago First seen · 59 lines · 103 tokens per session scan A 392f12e392cc
campaign-story is a skill published in the GitHub repository pnp/sharepoint-skills (137 stars, last pushed yesterday), licensed MIT. It adds 103 tokens to every session and 1,015 once invoked, about $0.0004 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-13.
Other skills, from other repositories
html-ppt-hermes-cyber-terminal
OpenDesign + BYOK: choosing and wiring your own model, hands-on — cost, quality, and the routing decision. Built as a decision-grade AI literacy deck for engineers, IT, applied-AI teams.
skill-doc-delivery
Convert markdown to DOCX, PPTX, XLSX, PDF office documents — use when you need exportable deliverables.
skill-writing-plans
Create zero-context implementation plans with bite-sized tasks — use for multi-step feature planning.
go-testing
Trigger: Go tests, go test coverage, Bubbletea teatest, golden files. Apply focused Go testing patterns.
bf-to-agents-sdk-dotnet-migration
Use when migrating a Bot Framework .NET SDK bot to Microsoft 365 Agents SDK. Triggered by projects that depend on packages: Microsoft.Bot.Builder or Microsoft.Bot.Builder.Integration.AspNet.Core that want to migrate to Agents SDK.
threejs-textures
Three.js textures - texture types, UV mapping, environment maps, texture settings. Use when working with images, UV coordinates, cubemaps, HDR environments, or texture optimization.